Rlaif: Scaling Reinforcement Learning from Human Feedback with AI Feedback (arxiv.org)

1 points by maccaw 3y ago ↗ HN

0 comments

[ 3.1 ms ] story [ 16.7 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats